RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Phi 3 mini 4k instruct run on the L40S?

Yes. At 8K context the best fit is F16, using about 10.6 GB of the 45.6 GB usable on the L40S. Estimated speed ceiling: ~113 tokens/sec.

Memory by quant and context

Quant4K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •3.3 GB Fits610
3-bit (Q3_K_M) •3.8 GB Fits442
4-bit (Q4_K_M) •4.2 GB Fits361
5-bit (Q5_K_M) •4.6 GB Fits307
6-bit (Q6_K) •4.9 GB Fits276
8-bit (Q8_0) •5.7 GB Fits213
16-bit (F16/BF16)9.1 GB Fits113

• real GGUF file size from bartowski/Phi-3.1-mini-4k-instruct-GGUF. Speed is a bandwidth ceiling (864 GB/s), not a benchmark. Methodology.

More

Phi 3 mini 4k instruct on every GPU and Mac · Every model that runs on the L40S · Other models that fit 48 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (microsoft/Phi-3-mini-4k-instruct), NVIDIA specs. Data as of 2026-11-17.